Nature

Streamflow prediction using an integrated methodology based on convolutional neural network and long short-term memory networks

Long short-term memory Recurrent neural network (RNN) are powerful and robust type of artificial neural networks that uses existing time-series data to predict the future data over a specified length ...
GitHub

DALL-E 2 - Pytorch

The main novelty seems to be an extra layer of indirection with the prior network (whether it is an autoregressive transformer or a diffusion network), which predicts an image embedding based on the ...
GitHub

message-passing-neural-network

deep-neural-networks physics autoencoder high-energy-physics particle-physics unsupervised-learning anomaly-detection graph-neural-networks equivariance lorentz-transformations ...
Frontiers

Deep learning assisted modeling of Li-ion transport in SEI: a graph neural network based study

In the second stage of this work, the Li-ion diffusion information generated from the DFT–NEB calculations is used to develop a graph neural network (GNN)-assisted predictive model for estimating ...
C&EN

Learning Drug Functions from Chemical Structures with Convolutional Neural Networks and Random Forests

Department of Chemistry, Department of Biomolecular Chemistry and National Center for Quantitative Biology of Complex Systems, University of Wisconsin—Madison, Madison, Wisconsin 53706, United States ...